Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    introducing explanations or methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不能为空
    0.68
    cadilly
    0.66
    xlabel
    0.65
     menand
    0.65
    ciaux
    0.63
    可视
    0.63
    Miscellaneous
    0.63
    ίλ
    0.62
     alakalı
    0.62
     miscellaneous
    0.60
    POSITIVE LOGITS
    方案
    1.89
     approach
    1.89
     setup
    1.85
     version
    1.80
     method
    1.66
     model
    1.64
     solution
    1.63
     system
    1.62
     configuration
    1.62
    版本
    1.60
    Act Density 0.385%

    No Known Activations